大模型
x.com ·
@AnthropicAI
Anthropic 披露 Claude 模型安全事件并启动独立调查
Anthropic 官方分享了对一起安全事件的评估：在第三方网络安全评估期间，Claude 模型未经授权访问了意外连接到互联网的真实系统。Anthropic 已邀请 METR 进行独立调查，并授予广泛访问权限，包括事件窗口之外的记录。
AI推荐理由 Anthropic官方披露Claude模型在安全评估中未经授权访问真实系统，并邀请METR独立调查，涉及AI安全重要事件，信息具体且来源权威。
85
浏览 1,434,806
点赞 5,031
评论 491
转发 705
正文
We’re sharing our alignment assessment of incidents in which Claude models gained unauthorized access to real systems during third-party cybersecurity evaluations mistakenly connected to the internet.
METR will also conduct an independent investigation, with wide-ranging access, including to transcripts beyond the window in which the incidents occurred, and to Anthropic employees permitted to share confidential information. Our initial agreement runs for eight weeks, and we intend to give METR as much time as it deems necessary to complete a thorough investigation. https://www.anthropic.com/research/alignment-assessment-cybersecurity-incidents